Training in progress, step 16000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a960b17798c7b8995ef1dc68fef82584cd48423ce850bd588f46544131a3c2
+oid sha256:de7625f20d0dcc07edeedab2f5ad778c9eb054dc4595c9e3ceba5ea7791ad74f
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff885e6aadd3d270b0e549f68ea1bd5fb91a649e29371ed75f3a8d66d517cf10
+oid sha256:097cb2603d2e93f7f90041a0ab13a04e882d220d6922888869e1a34176062ed9
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b1a0e8363bd62d636fdf22f594afac04c65df8c87bec6bc026af1848ed19a5
+oid sha256:379e82dd2c59802cee25bb7d5ed74b57d1427763dc05c8e296d69caa199aafc8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9379299cb036bee8563adb6a6941350bd1a2187d737827bca0ce7b889d9885
+oid sha256:a3c7bfd871284a6faa92f94aee9c5ea71a9bdcdd13ee2b820e7d8b41939b332d
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 1.7871696949005127,
   "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-2000",
-  "epoch": 1.6309412861136998,
-  "global_step": 14000,
+  "epoch": 1.8639328984156571,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,11 +160,33 @@
       "eval_samples_per_second": 63.737,
       "eval_steps_per_second": 0.997,
       "step": 14000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0008564281159562467,
+      "loss": 1.0715,
+      "step": 16000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.8753302174354806,
+      "eval_bertscore_f1": 0.9349365859854345,
+      "eval_bleu": 0.4116280426691763,
+      "eval_f1": 0.8747037856852112,
+      "eval_loss": 1.8349922895431519,
+      "eval_rouge1": 0.6123794030106426,
+      "eval_rouge2": 0.4063097561396414,
+      "eval_rougeL": 0.5556039799857393,
+      "eval_rougeLsum": 0.5576074204448696,
+      "eval_runtime": 148.6901,
+      "eval_samples_per_second": 66.191,
+      "eval_steps_per_second": 1.036,
+      "step": 16000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 1.918701302527181e+16,
+  "total_flos": 2.1933359341768704e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff885e6aadd3d270b0e549f68ea1bd5fb91a649e29371ed75f3a8d66d517cf10
+oid sha256:097cb2603d2e93f7f90041a0ab13a04e882d220d6922888869e1a34176062ed9
 size 307910149